{"id":"W2885169382","doi":"10.1111/emip.12211","title":"How Robust Are Cross‐Country Comparisons of PISA Scores to the Scaling Model Used?","year":2018,"lang":"en","type":"article","venue":"Educational Measurement Issues and Practice","topic":"Online Learning and Analytics","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Criticism; Robustness (evolution); Underpinning; Item response theory; Psychology; Test (biology); Cross country; Psychometrics; Political science; Developmental psychology; Economics; Demographic economics; Engineering","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001391535,0.0001000907,0.0001168024,0.00005065544,0.0003299742,0.0005123011,0.0003984438,0.00002893876,0.000007386586],"category_scores_gemma":[0.002075884,0.00007472435,0.00002486233,0.0002445434,0.00008539332,0.0005280875,0.00009570461,0.0001333374,0.00001503834],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003151627,"about_ca_system_score_gemma":0.0002116854,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001239838,"about_ca_topic_score_gemma":0.00007187411,"domain_scores_codex":[0.9986129,0.0001263701,0.0001627559,0.000243162,0.000700334,0.0001544801],"domain_scores_gemma":[0.9980717,0.0003478651,0.0002080062,0.0003328501,0.0009592777,0.00008035629],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000248513,0.002645121,0.1090599,0.0003144594,0.0005599114,0.000002831286,0.029784,0.2281277,0.002448642,0.3478672,0.2693268,0.00961485],"study_design_scores_gemma":[0.0004008404,0.000234534,0.0497829,0.0003613918,0.0001257088,0.00003367427,0.003131678,0.4887249,0.0008174491,0.003682131,0.4522132,0.0004915953],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.02731458,0.002817017,0.2651742,0.7021272,0.0008571699,0.0002327467,0.00001135517,0.00004648148,0.001419336],"genre_scores_gemma":[0.8978047,0.00003590594,0.09946898,0.001008572,0.0006902865,0.000006493733,0.000002126218,0.000006492901,0.0009763939],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8704902,"threshold_uncertainty_score":0.4940132,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1301498662001438,"score_gpt":0.3787550552457036,"score_spread":0.2486051890455598,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}